GGUF models by tensorblock

4944 GGUF models quantized by tensorblock on Hugging Face. Sizes run from 1M to 72.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Onnx Internal Testing Tiny Random LlamaForCausalLM
Llama · tensorblock
Params4M
Context128K
Smallest0.0 GB
GGUF
GE
gemma 2 9b instruct
Gemma · tensorblock
Params9.24B
Context8K
Smallest3.8 GB
GGUF
YI
01 Ai Yi 34B
Yi · tensorblock
Params34.4B
Context4K
Smallest12.8 GB
GGUF
DE
Deepseek Ai Deepseek Llm 7b Chat
DeepSeek · tensorblock
Params6.91B
Context4K
Smallest2.7 GB
GGUF
QW
Mlx Community Qwen2.5 Coder 32B Instruct Bf16
Qwen · tensorblock
Params32.8B
Context32K
Smallest12.3 GB
CodingTool use
QW
Qwen Qwen3 4B
Qwen · tensorblock
Params4.02B
Context40K
Smallest1.7 GB
ReasoningTool use
PO
LumiOpen Poro 34B
Poro · tensorblock
Params35.1B
Context7K
Smallest13.4 GB
Coding
QW
Qwen Qwen1.5 4B
Qwen · tensorblock
Params3.95B
Context32K
Smallest1.6 GB
GGUF
QW
Qwen Qwen3 30B A3B Instruct 2507
Qwen · tensorblock
Params30.5B
Context256K
Smallest11.3 GB
ReasoningTool use
QW
Qwen2 7B
Qwen · tensorblock
Params7.62B
Context128K
Smallest3.0 GB
GGUF
MI
ANIMA Phi Neptune Mistral 7B
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
LL
Meditsolutions Llama 3.2 SUN 2.5B Chat
Llama · tensorblock
Params2.47B
Context128K
Smallest1.0 GB
ReasoningTool use
OC
Occiglot Occiglot 7b It En Instruct
Occiglot · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · tensorblock
Params32.8B
Context128K
Smallest12.3 GB
ReasoningTool use
SO
Mssma Ko Solar 10.7b v0.4
Solar · tensorblock
Params10.9B
Context2K
Smallest4.1 GB
GGUF
PH
Phi 4 Mini Instruct
Phi · tensorblock
Params3.84B
Context128K
Smallest1.7 GB
CodingTool use
QW
Qwen Qwen2.5 14B Instruct
Qwen · tensorblock
Params14.8B
Context32K
Smallest5.8 GB
Tool use
YI
Instruct Yi 6B Dolly CodeAlpaca
Yi · tensorblock
Params6.06B
Context4K
Smallest2.3 GB
GGUF
CA
Calcium Opus 14B Elite 1M
Calcium · tensorblock
Params14.8B
Context986K
Smallest5.8 GB
ReasoningTool use
TA
RUCKBReasoning TableLLM 7b
Tablellm · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
CodingReasoning
LL
Llama 3.3 70B Instruct ablated
Llama · tensorblock
Params70.6B
Context128K
Smallest26.4 GB
Tool use
QW
Qwen Qwen1.5 1.8B Chat
Qwen · tensorblock
Params1.84B
Context32K
Smallest0.8 GB
GGUF
LL
Llama 2 13b Hf
Llama · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
LL
Meta Llama Llama 3.2 1B Instruct
Llama · tensorblock
Params1.24B
Context128K
Smallest0.6 GB
Tool use
LL
Llama 3.2 8B Instruct
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Tool use
LL
Llama 3.2 Rabbit Ko 1B Instruct
Llama · tensorblock
Params1.24B
Context128K
Smallest0.6 GB
GGUF
GR
Ibm Granite Granite 8b Code Base 4k
Granite · tensorblock
Params8.05B
Context4K
Smallest3.1 GB
Coding
LL
llama3 small
Llama · tensorblock
Params177M
Context8K
Smallest0.1 GB
GGUF
GR
Ibm Granite Granite 3b Code Base 2k
Granite · tensorblock
Params3.48B
Context2K
Smallest1.3 GB
Coding
LL
dolphin 2.9.3 llama 3 8b
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF

Keep browsing